[Fix] Failed to start vLLM service using multi-node launch scripts under CUDA data parallelism#670
Merged
mag1c-h merged 1 commit intoModelEngine-Group:developfrom Jan 23, 2026
Conversation
…nder CUDA data parallelism
sumingZero
requested review from
Infinite666,
harrisonyhq,
mag1c-h and
ygwpz
as code owners
flesher0813
changed the title
mag1c-h
approved these changes
Jan 23, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
…nder CUDA data parallelism
Purpose
What this PR does / why we need it?
When launching a multi-node data-parallel service using run_vllm.sh, the startup fails due to missing
--data-parallel-backendand--data-parallel-size-localarguments. This commit fixes the issue by adding the missing parameters.Test
How was this patch tested?
Verified that the script can successfully launch the service in a dual-node DP=4, TP=4 configuration.